Revisit Lmser and its further development based on convolutional layers
This work provides an incremental update to the Lmser network by adapting it to modern deep learning contexts, potentially benefiting researchers in image processing and neural networks.
The paper revisited the Lmser network, originally proposed in 1991, by developing it with multiple convolutional layers for image-related tasks, and confirmed its functions through experiments on image recognition, reconstruction, and association recall, showing promising performance.
Proposed in 1991, Least Mean Square Error Reconstruction for self-organizing network, shortly Lmser, was a further development of the traditional auto-encoder (AE) by folding the architecture with respect to the central coding layer and thus leading to the features of symmetric weights and neurons, as well as jointly supervised and unsupervised learning. However, its advantages were only demonstrated in a one-hidden-layer implementation due to the lack of computing resources and big data at that time. In this paper, we revisit Lmser from the perspective of deep learning, develop Lmser network based on multiple convolutional layers, which is more suitable for image-related tasks, and confirm several Lmser functions with preliminary demonstrations on image recognition, reconstruction, association recall, and so on. Experiments demonstrate that Lmser indeed works as indicated in the original paper, and it has promising performance in various applications.